© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14159
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially that associated with measurements and statistics, sometimes including associated units or symbols like plus/minus signs.

    oai_token-act-pair · gemini-2.0-flash

    Single digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.79
     خارجية
    -0.74
    LookAnd
    -0.73
     समीक्षक
    -0.73
     CreateTagHelper
    -0.71
    twimg
    -0.70
    PerformLayout
    -0.69
     ExecuteAsync
    -0.66
     defaultstate
    -0.66
    TagMode
    -0.65
    POSITIVE LOGITS
    ENAME
    0.47
    IBUS
    0.46
     HES
    0.46
    illère
    0.46
     aidé
    0.45
    idazole
    0.45
     apsau
    0.45
     McIntyre
    0.44
    olson
    0.44
    퇴
    0.44
    Activations Density 2.033%

    No Known Activations